A novel approach for predicting microbe-disease associations by bi-random walk on the heterogeneous network

• Published in: PloS one 2017-09, Vol.12 (9), p.e0184394-e0184394
• Main Authors: Zou, Shuai, Zhang, Jingpu, Zhang, Zuping
• Format: Article
• Language: English
• Subjects: Algorithms; Asthma; Biology and Life Sciences; Case studies; Computation; Computational Biology - methods; Computer applications; Computer Simulation; Development and progression; Diagnosis; Genetic Association Studies; Genetic Predisposition to Disease - genetics; Immunology; Infection; Inflammatory bowel disease; Inflammatory bowel diseases; Information science; Intestine; Kinetics; Logistic Models; Mathematical models; Medicine and Health Sciences; Microbiota (Symbiotic organisms); Microorganisms; Pathogenesis; Performance prediction; Physical Sciences; Physiological aspects; Prediction models; Prognosis; Random walk; Research and Analysis Methods; Risk Factors; Similarity; Streptococcus infections; Studies
• ISSN: 1932-6203; 1932-6203
• DOI: 10.1371/journal.pone.0184394

Since the microbiome has a significant impact on human health and disease, microbe-disease associations can be utilized as a valuable resource for understanding disease pathogenesis and promoting disease diagnosis and prognosis. Accordingly, it is necessary for researchers to achieve a comprehensive and deep understanding of the associations between microbes and diseases. Nevertheless, to date, little work has been achieved in implementing novel human microbe-disease association prediction models. In this paper, we develop a novel computational model to predict potential microbe-disease associations by bi-random walk on the heterogeneous network (BiRWHMDA). The heterogeneous network was constructed by connecting the microbe similarity network and the disease similarity network via known microbe-disease associations. Microbe similarity and disease similarity were calculated by the Gaussian interaction profile kernel similarity measure; moreover, a logistic function was applied to regulate disease similarity. Additionally, leave-one-out cross validation and 5-fold cross validation were implemented to evaluate the predictive performance of our method; both cross validation methods performed well. The leave-one-out cross validation experiment results illustrate that our method outperforms other previously proposed methods. Furthermore, case studies on asthma and inflammatory bowel disease prove the favorable performance of our method. In conclusion, our method can be considered as an effective computational model for predicting novel microbe-disease associations.